Popular repositories Loading

1. OpenPipe OpenPipe Public

   Turn expensive prompts into cheap fine-tuned models

   TypeScript 2.6k 148

2. ART ART Public

   Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen2.5, Qwen3, Llama, Kimi, and more!

   Python 2.1k 132

3. deductive-reasoning deductive-reasoning Public

   Train your own SOTA deductive reasoning model

   Python 99 6

4. pii-redaction pii-redaction Public

   Detect and redact PII locally with SOTA performance

   Python 59 10

5. rl-experiments rl-experiments Public

   OpenPipe Reinforcement Learning Experiments

   Jupyter Notebook 27 4

6. Summary-RL Summary-RL Public

   Train an agent to generate high quality summaries

   Jupyter Notebook 21 4